© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1870
    Prev
    Next
    INDEX
    Explanations

    calendar dates, numbers, file headers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens (sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Eddy
    -0.78
    biskan
    -0.76
    ionato
    -0.75
     クリップ
    -0.75
    ↩
    -0.74
     Fluorescent
    -0.74
     Stove
    -0.73
     każdym
    -0.70
     SECRET
    -0.70
     SILVER
    -0.69
    POSITIVE LOGITS
     nhôm
    0.75
    度假
    0.69
    太平洋
    0.68
    cere
    0.68
     somehow
    0.68
    abad
    0.67
    urfs
    0.67
     кори
    0.67
    わかり
    0.65
     feasible
    0.65
    Activations Density 0.051%

    No Known Activations